Latest news with #ALOHA
Mint
a day ago
- Mint
Google Gemini AI model brings real-time intelligence to bi-arm robots
Google DeepMind has announced the launch of a new artificial intelligence model tailored for robotics, capable of functioning entirely on a local device without requiring an active data connection. NamedGemini Robotics On-Device, the advanced model is designed to enable bi-arm robots to carry out complex tasks in real-world environments by combining voice, language and action (VLA) processing. In a blog post, Carolina Parada, Senior Director and Head of Robotics at Google DeepMind, introduced the new model, highlighting its low-latency performance and flexibility. As it operates independently of the cloud, the model is especially suited to latency-sensitive environments and real-time applications where constant internet connectivity is not feasible. Currently, access to the model is restricted to participants of Google's trusted tester programme. Developers can experiment with the AI system through the Gemini Robotics software development kit (SDK) and the company's MuJoCo physics simulator. Although Google has not disclosed specific details about the model's architecture or training methodology, it has outlined the model's robust capabilities. Designed for bi-arm robotic platforms, Gemini Robotics On-Device requires minimal computing resources. Remarkably, the system can adapt to new tasks using only 50 to 100 demonstrations, a feature that significantly accelerates deployment in diverse settings. In internal trials, the model demonstrated the ability to interpret natural language commands and perform a wide array of sophisticated tasks, from folding clothes and unzipping bags to handling unfamiliar objects. It also successfully completed precision tasks such as those found in industrial belt assembly, showcasing high levels of dexterity. Though originally trained on ALOHA robotic systems, Gemini Robotics On-Device has also been adapted to work with other bi-arm robots including Franka Emika's FR3 and Apptronik's Apollo humanoid robot. According to the American tech giant, the model exhibited consistent generalisation performance across different platforms, even when faced with out-of-distribution tasks or multi-step instructions.
Hans India
2 days ago
- Hans India
Google's Gemini AI Now Powers Robots Without Internet Access
New Delhi: In a major leap for edge robotics, Google DeepMind has introduced Gemini Robotics On-Device, a new AI model that enables robots to function without needing an internet connection. This development brings greater autonomy, speed, and data privacy to real-world robotics, especially in locations where connectivity is limited or restricted. Carolina Parada, head of robotics at Google DeepMind, described the release as a practical shift toward making robots more independent. 'It's small and efficient enough to run directly on a robot,' she told The Verge. 'I would think about it as a starter model or as a model for applications that just have poor connectivity.' Despite being a more compact version of its cloud-based predecessor, the on-device variant is surprisingly robust. 'We're actually quite surprised at how strong this on-device model is,' Parada added, pointing to its effectiveness even with minimal training. The model can perform tasks almost immediately after deployment and requires only 50 to 100 demonstrations to learn new ones. Initially developed using Google's ALOHA robot, it has since been adapted to other robotic systems including Apptronik's Apollo humanoid and the dual-armed Franka FR3. Tasks such as folding laundry or unzipping bags can now be executed entirely on-device, without latency caused by cloud interaction. This is a key differentiator compared to other advanced systems like Tesla's Optimus, which still rely on cloud connectivity for processing. The local processing aspect is a highlight for sectors that prioritize data security, such as healthcare or sensitive industrial settings. 'When we play with the robots, we see that they're surprisingly capable of understanding a new situation,' Parada noted, emphasizing the model's flexibility and adaptability. However, Google acknowledges some trade-offs. Unlike the cloud-based Gemini Robotics suite, the on-device model lacks built-in semantic safety tools. Developers are encouraged to implement safety mechanisms independently, using APIs like Gemini Live and integrating with low-level robotic safety systems. 'With the full Gemini Robotics, you are connecting to a model that is reasoning about what is safe to do, period,' said Parada. This announcement follows Google's recent launch of the AI Edge Gallery, an Android-based app that lets users run generative AI models offline using the compact Gemma 3 1B model. Much like Gemini Robotics On-Device, this app focuses on privacy-first, low-latency experiences using frameworks like TensorFlow Lite and open-source models from Hugging Face. Together, these launches signal Google's broader move to decentralize AI, bringing high-performance intelligence directly to user devices—be it phones or robots.
India Today
2 days ago
- India Today
Google's new Gemini AI can power robots and make them work without internet
Google DeepMind has launched a new version of its Gemini Robotics AI model that allows robots to operate entirely without internet access. Called Gemini Robotics On-Device, the system is designed to power robots in real-world settings where speed, autonomy, and privacy are crucial. This update marks a significant shift from earlier models that relied on cloud connectivity. By enabling robots to process information and make decisions on the device itself, Google hopes to make robotics more practical in offline environments such as remote areas, secure facilities, and latency-sensitive small and efficient enough to run directly on a robot,' said Carolina Parada, head of robotics at Google DeepMind, in a statement to The Verge. 'I would think about it as a starter model or as a model for applications that just have poor connectivity.'Despite being a smaller variant, the on-device version holds its own. 'We're actually quite surprised at how strong this on-device model is,' Parada Robotics On-Device brings several new features to the table. The model can carry out tasks straight out of the box and learn new ones from as few as 50 to 100 demonstrations. The model was initially trained using Google's ALOHA robot, but it has since been successfully adapted for use with other robotic systems, such as Apptronik's Apollo humanoid and the dual-armed Franka Google says that it can perform detailed actions such as folding clothes or unzipping bags, all while running low-latency inference perspective, Tesla's humanoid robot, Optimus, can also do all those things – folding a t-shirt, boiling an egg, dancing, etc – but it needs an internet connection to send data to cloud servers. However, in the case of Gemini Robotics On-Device, a standout feature is that all data is processed locally. That makes it particularly useful for privacy-sensitive applications, such as healthcare and industrial automation, where data security is a concern.'When we play with the robots, we see that they're surprisingly capable of understanding a new situation,' said Parada, highlighting the model's flexibility and the system does not rely on the cloud, it also keeps functioning in places with weak or no connectivity, making it highly reliable. 'It's drawing from Gemini's multimodal world understanding in order to do a completely new task,' Parada unlike the cloud-based hybrid version, the on-device model does not include built-in semantic safety tools. Google recommends that developers implement their own safety systems, including using Gemini Live APIs and connecting to low-level safety the full Gemini Robotics, you are connecting to a model that is reasoning about what is safe to do, period,' said launch comes shortly after Google introduced the AI Edge Gallery, an Android app that lets users run AI models offline on their smartphones. Powered by the compact Gemma 3 1B model, the app allows users to generate images, write text, and interact with AI tools directly on their devices – no internet like Gemini Robotics On-Device, AI Edge Gallery focuses on privacy and low-latency performance. It uses open-source models from platforms like Hugging Face and technologies like TensorFlow Lite to ensure smooth experiences across a range of devices.- Ends
The Hindu
2 days ago
- Business
- The Hindu
Google DeepMind unveils on-device robotics model
Google DeepMind has unveiled a Gemini Robotics on-device Vision Language Action (VLA) model that can run locally on robotic devices. The AI model is built for general purpose tasks and can run without the internet. This is Google's first VLA model that has made available for fine-tuning. Developers can sign up for the tester programme and access the software kits. This new model comes two months after the search giant released its Gemini Robotics model based on Gemini 2.0's multimodal reasoning and real-world understanding of the physical world. The flagship model can run both on-device and on the cloud, and is built for bi-pedal robots. The model can also be customised for different robotic form factors. 'While we trained our model only for ALOHA robots, we were able to further adapt it to bi-arm Franka FR3 robot and the Apollo humanoid robot by Apptronik,' the company said in a blog post. With the bi-arm Franks, the VLA model can perform other tasks like folding clothes or work on industrial belt assembly tasks too.
Yahoo
2 days ago
- Yahoo
Google rolls out new Gemini model that can run on robots locally
Google DeepMind on Tuesday released a new language model called Gemini Robotics On-Device that can run tasks locally on robots without requiring an internet connection. Building on the company's previous Gemini Robotics model that was released in March, Gemini Robotics On-Device can control a robot's movements. Developers can control and fine-tune the model to suit various needs using natural language prompts. In benchmarks, Google claims the model performs at a level close to the cloud-based Gemini Robotics model. The company says it outperforms other on-device models in general benchmarks, though it didn't name those models. In a demo, the company showed robots running this local model doing things like unzipping bags and folding clothes. Google says that while the model was trained for ALOHA robots, it later adapted it to work on a bi-arm Franka FR3 robot and the Apollo humanoid robot by Apptronik. Google claims the bi-arm Franka FR3 was successful in tackling scenarios and objects it hadn't 'seen' before, like doing assembly on an industrial belt. Google DeepMind is also releasing a Gemini Robotics SDK. The company said developers can show robots 50 to 100 demonstrations of tasks to train them on new tasks using these models on the MuJoCo physics simulator. Other AI model developers are also dipping their toes in robotics. Nvidia is building a platform to create foundation models for humanoids; Hugging Face is not only developing open models and datasets for robotics, it is actually working on robots too; and Mirae Asset-backed Korean startup RLWRLD is working on creating foundational models for robots.
